一种QoS感知的服务全局优化选择算法  

QoS-aware service selection global optimization algorithm

作　　者：苏凯[1] 马良荔[1] 郭晓明[1] 孙煜飞[1] 

机构地区：[1]海军工程大学计算机工程系,湖北武汉430033

出　　处：《华中科技大学学报（自然科学版）》2014年第4期72-76,共5页Journal of Huazhong University of Science and Technology(Natural Science Edition)

基　　金：总装预研基金资助项目(9140A27040413JB11407);国家自然科学基金资助项目(61170217)

摘　　要：将服务选择问题建模为带QoS约束的非线性最优化问题,并提出了一种参数自适应的改进遗传算法(IPAGA).构造了基于双曲正切函数的非线性参数变换函数,当迭代次数或种群多样性程度增加时,使遗传算法的交叉和变异概率相应地非线性递减,以保证算法的全局收敛性和收敛速度.实验结果表明:算法能够快速搜索出全局近似最优解,具有很高的有效性和可行性.The service selection problem was modeled as a problem of nonlinear optimization with QoS （quality of service） constraints. Then, an improved parameter adaptive genetic algorithm （IPAGA） was proposed. A nonlinear parameter transforming function based on the hyperbolic tangent function was constructed, which made the crossover probability and the mutation probability decrease nonlin- early with the increasing of iterations and population diversity. Thereby, the convergence speed and the global convergence were ensured. The experimental results show that an approximate optimal re- sult can be searched out quickly. The efficiency and feasibility of our approach are demonstrated in the experimental evaluation.

关 键 词：服务动态组合 遗传算法 服务选择 全局优化 服务质量约束 参数自适应 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]